Hand Motion Recognition

Recognizes 25 hand motions performed in front of the camera (swipes, thumb up, stop sign, and more). The model is trained on the Jester dataset. Used for touchless control and game input. Unlike the gesture recognition of Hand Tracking, which classifies a hand shape in a single frame, hand motion recognition classifies movement over time.

Commands

Command	Description
Specific Hand Motion?	Checks whether the target hand motion is detected at or above the threshold.
Recognition Result	Writes the name and probability of the most probable hand motion.
All Results	Writes every recognition result, ordered by probability, as JSON.

Settings

Setting	Description
Target Hand Motion	The motion watched by Specific Hand Motion?. One of 25; the default is Swiping Left.
Detection Threshold (%)	Probability at or above this value counts as the motion. 10 to 100, default 50.

Output Variables

Field	Type	Value
Hand Motion Name	Text	English name of the most probable hand motion.
Confidence	Number	Probability of the recognized motion, 0 to 100.
Hand Motion Matched	Digital	True when Specific Hand Motion? finds the target motion at or above the threshold.
JSON Result	Text	Array of every recognition result.

JSON Output

An array with, per result, label, confidence (0 to 100), and the model class number index, ordered from the highest probability.

[
  { "label": "Swiping Left", "confidence": 85, "index": 0 },
  { "label": "Thumb Up", "confidence": 10, "index": 1 }
]

The 25 hand motions

Swiping Left, Swiping Right, Swiping Down, Swiping Up, Pushing Hand Away, Pulling Hand In, Sliding Two Fingers Left, Sliding Two Fingers Right, Sliding Two Fingers Down, Sliding Two Fingers Up, Pushing Two Fingers Away, Pulling Two Fingers In, Rolling Hand Forward, Rolling Hand Backward, Turning Hand Clockwise, Turning Hand Counterclockwise, Zooming In With Full Hand, Zooming Out With Full Hand, Zooming In With Two Fingers, Zooming Out With Two Fingers, Thumb Up, Thumb Down, Shaking Hand, Stop Sign, Drumming Fingers